Collaborating NLP Agents

classic project

Author

Abstract

The project involves the design and implementation of a multi-agent system for training classifiers with different configurations given a parameter space. Using a master-slave architecture, the system searches the parameter space by random sampling and trains the classifiers for named-entity recognition on the CoNLL-2003 dataset in a round-robin manner. The best trained classifier is then determined and evaluated on the test set. Results show that the proposed multi-agent system is able to search the parameter space efficiently.

Outcome

Tags:

Course

— a.y.

2021/2022

— credits

6

— cycle

2nd cycle

— language

wgb.gif

Teachers

— professor

Andrea Omicini

— other professors

Roberta Calegari

Context

— university

Alma Mater Studiorum-Università di Bologna

— campus

Bologna

— department / faculty / school

DISI

— 2nd cycle

 9063 Artificial Intelligence 

URLs & IDs

AMS Page
course on Virtuale
virtual room
Course Timetable

— course ID

91267

Related Courses

— components

Multi-Agent Systems (Module 1) (2nd Cycle, 2021/2022) — Andrea Omicini  |  Multi-Agent Systems (Module 2) (2nd Cycle, 2021/2022) — Roberta Calegari

— related

Project Work in Multi-Agent Systems (2nd Cycle, 2021/2022) — Andrea Omicini

Partita IVA: 01131710376 - Copyright © 2008-2022 APICe@DISI Research Group - PRIVACY